Quality adaptive least squares trained filters for video compression artifacts removal using a no-reference block visibility metric

Ling Shao (Corresponding author), Jingnan Wang, Ihor Kirenko, Gerard de Haan

Research output: Contribution to journalArticleAcademicpeer-review

13 Citations (Scopus)

Abstract

Compression artifacts removal is a challenging problem because videos can be compressed at different qualities. In this paper, a least squares approach that is self-adaptive to the visual quality of the input sequence is proposed. For compression artifacts, the visual quality of an image is measured by a no-reference block visibility metric. According to the blockiness visibility of an input image, an appropriate set of filter coefficients that are trained beforehand is selected for optimally removing coding artifacts and reconstructing object details. The performance of the proposed algorithm is evaluated on a variety of sequences compressed at different qualities in comparison to several other de-blocking techniques. The proposed method outperforms the others significantly both objectively and subjectively.

Original languageEnglish
Pages (from-to)23-32
Number of pages10
JournalJournal of Visual Communication and Image Representation
Volume22
Issue number1
DOIs
Publication statusPublished - 1 Jan 2011

Keywords

  • Adaptive filtering
  • Blocking artifact reduction
  • Compression artifacts removal
  • Image enhancement
  • Least squares filter
  • No-reference quality metric
  • Noise reduction
  • Picture quality improvement

Fingerprint

Dive into the research topics of 'Quality adaptive least squares trained filters for video compression artifacts removal using a no-reference block visibility metric'. Together they form a unique fingerprint.

Cite this